{
  "best_metric": 1.943039059638977,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.03423192126658109,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00017115960633290543,
      "grad_norm": 0.3355412781238556,
      "learning_rate": 5e-06,
      "loss": 2.1057,
      "step": 1
    },
    {
      "epoch": 0.00017115960633290543,
      "eval_loss": 2.140085220336914,
      "eval_runtime": 258.9714,
      "eval_samples_per_second": 37.996,
      "eval_steps_per_second": 18.998,
      "step": 1
    },
    {
      "epoch": 0.00034231921266581085,
      "grad_norm": 0.29723942279815674,
      "learning_rate": 1e-05,
      "loss": 2.0679,
      "step": 2
    },
    {
      "epoch": 0.0005134788189987163,
      "grad_norm": 0.31555816531181335,
      "learning_rate": 1.5e-05,
      "loss": 2.2761,
      "step": 3
    },
    {
      "epoch": 0.0006846384253316217,
      "grad_norm": 0.25562918186187744,
      "learning_rate": 2e-05,
      "loss": 1.881,
      "step": 4
    },
    {
      "epoch": 0.0008557980316645272,
      "grad_norm": 0.2628590166568756,
      "learning_rate": 2.5e-05,
      "loss": 2.0202,
      "step": 5
    },
    {
      "epoch": 0.0010269576379974327,
      "grad_norm": 0.25577813386917114,
      "learning_rate": 3e-05,
      "loss": 1.8699,
      "step": 6
    },
    {
      "epoch": 0.0011981172443303381,
      "grad_norm": 0.2143595963716507,
      "learning_rate": 3.5e-05,
      "loss": 1.7798,
      "step": 7
    },
    {
      "epoch": 0.0013692768506632434,
      "grad_norm": 0.24432000517845154,
      "learning_rate": 4e-05,
      "loss": 2.0537,
      "step": 8
    },
    {
      "epoch": 0.0015404364569961489,
      "grad_norm": 0.2208261489868164,
      "learning_rate": 4.5e-05,
      "loss": 1.7771,
      "step": 9
    },
    {
      "epoch": 0.0017115960633290544,
      "grad_norm": 0.22592778503894806,
      "learning_rate": 5e-05,
      "loss": 1.9607,
      "step": 10
    },
    {
      "epoch": 0.0018827556696619598,
      "grad_norm": 0.22352802753448486,
      "learning_rate": 5.500000000000001e-05,
      "loss": 2.0779,
      "step": 11
    },
    {
      "epoch": 0.0020539152759948653,
      "grad_norm": 0.22015997767448425,
      "learning_rate": 6e-05,
      "loss": 2.0472,
      "step": 12
    },
    {
      "epoch": 0.002225074882327771,
      "grad_norm": 0.20282255113124847,
      "learning_rate": 6.500000000000001e-05,
      "loss": 2.0319,
      "step": 13
    },
    {
      "epoch": 0.0023962344886606763,
      "grad_norm": 0.18487398326396942,
      "learning_rate": 7e-05,
      "loss": 2.1545,
      "step": 14
    },
    {
      "epoch": 0.0025673940949935813,
      "grad_norm": 0.15891127288341522,
      "learning_rate": 7.500000000000001e-05,
      "loss": 2.0743,
      "step": 15
    },
    {
      "epoch": 0.002738553701326487,
      "grad_norm": 0.15739785134792328,
      "learning_rate": 8e-05,
      "loss": 1.9694,
      "step": 16
    },
    {
      "epoch": 0.0029097133076593923,
      "grad_norm": 0.1441313922405243,
      "learning_rate": 8.5e-05,
      "loss": 1.874,
      "step": 17
    },
    {
      "epoch": 0.0030808729139922978,
      "grad_norm": 0.1597474068403244,
      "learning_rate": 9e-05,
      "loss": 2.0868,
      "step": 18
    },
    {
      "epoch": 0.0032520325203252032,
      "grad_norm": 0.16448548436164856,
      "learning_rate": 9.5e-05,
      "loss": 2.0087,
      "step": 19
    },
    {
      "epoch": 0.0034231921266581087,
      "grad_norm": 0.15660351514816284,
      "learning_rate": 0.0001,
      "loss": 2.0582,
      "step": 20
    },
    {
      "epoch": 0.003594351732991014,
      "grad_norm": 0.1746840476989746,
      "learning_rate": 9.999238475781957e-05,
      "loss": 1.9058,
      "step": 21
    },
    {
      "epoch": 0.0037655113393239197,
      "grad_norm": 0.17854997515678406,
      "learning_rate": 9.99695413509548e-05,
      "loss": 1.9869,
      "step": 22
    },
    {
      "epoch": 0.003936670945656825,
      "grad_norm": 0.18090517818927765,
      "learning_rate": 9.99314767377287e-05,
      "loss": 2.0419,
      "step": 23
    },
    {
      "epoch": 0.004107830551989731,
      "grad_norm": 0.15388450026512146,
      "learning_rate": 9.987820251299122e-05,
      "loss": 2.0196,
      "step": 24
    },
    {
      "epoch": 0.004278990158322636,
      "grad_norm": 0.15999741852283478,
      "learning_rate": 9.980973490458728e-05,
      "loss": 2.0682,
      "step": 25
    },
    {
      "epoch": 0.004450149764655542,
      "grad_norm": 0.13543976843357086,
      "learning_rate": 9.972609476841367e-05,
      "loss": 1.9447,
      "step": 26
    },
    {
      "epoch": 0.004621309370988447,
      "grad_norm": 0.14296641945838928,
      "learning_rate": 9.962730758206611e-05,
      "loss": 2.1334,
      "step": 27
    },
    {
      "epoch": 0.004792468977321353,
      "grad_norm": 0.13348829746246338,
      "learning_rate": 9.951340343707852e-05,
      "loss": 1.9633,
      "step": 28
    },
    {
      "epoch": 0.004963628583654257,
      "grad_norm": 0.13364166021347046,
      "learning_rate": 9.938441702975689e-05,
      "loss": 2.0228,
      "step": 29
    },
    {
      "epoch": 0.005134788189987163,
      "grad_norm": 0.1257980912923813,
      "learning_rate": 9.924038765061042e-05,
      "loss": 1.8989,
      "step": 30
    },
    {
      "epoch": 0.005305947796320068,
      "grad_norm": 0.13509519398212433,
      "learning_rate": 9.908135917238321e-05,
      "loss": 1.952,
      "step": 31
    },
    {
      "epoch": 0.005477107402652974,
      "grad_norm": 0.1233903169631958,
      "learning_rate": 9.890738003669029e-05,
      "loss": 1.9286,
      "step": 32
    },
    {
      "epoch": 0.005648267008985879,
      "grad_norm": 0.12037648260593414,
      "learning_rate": 9.871850323926177e-05,
      "loss": 1.982,
      "step": 33
    },
    {
      "epoch": 0.005819426615318785,
      "grad_norm": 0.10984398424625397,
      "learning_rate": 9.851478631379982e-05,
      "loss": 1.7714,
      "step": 34
    },
    {
      "epoch": 0.00599058622165169,
      "grad_norm": 0.12199705094099045,
      "learning_rate": 9.829629131445342e-05,
      "loss": 1.9782,
      "step": 35
    },
    {
      "epoch": 0.0061617458279845955,
      "grad_norm": 0.12401176989078522,
      "learning_rate": 9.806308479691595e-05,
      "loss": 2.08,
      "step": 36
    },
    {
      "epoch": 0.006332905434317501,
      "grad_norm": 0.12610073387622833,
      "learning_rate": 9.781523779815179e-05,
      "loss": 1.9806,
      "step": 37
    },
    {
      "epoch": 0.0065040650406504065,
      "grad_norm": 0.1307840496301651,
      "learning_rate": 9.755282581475769e-05,
      "loss": 2.1165,
      "step": 38
    },
    {
      "epoch": 0.006675224646983312,
      "grad_norm": 0.13169904053211212,
      "learning_rate": 9.727592877996585e-05,
      "loss": 1.9079,
      "step": 39
    },
    {
      "epoch": 0.0068463842533162175,
      "grad_norm": 0.13578273355960846,
      "learning_rate": 9.698463103929542e-05,
      "loss": 1.8204,
      "step": 40
    },
    {
      "epoch": 0.007017543859649123,
      "grad_norm": 0.14357295632362366,
      "learning_rate": 9.667902132486009e-05,
      "loss": 1.9466,
      "step": 41
    },
    {
      "epoch": 0.007188703465982028,
      "grad_norm": 0.14602960646152496,
      "learning_rate": 9.635919272833938e-05,
      "loss": 1.8532,
      "step": 42
    },
    {
      "epoch": 0.007359863072314934,
      "grad_norm": 0.16406601667404175,
      "learning_rate": 9.602524267262203e-05,
      "loss": 2.0449,
      "step": 43
    },
    {
      "epoch": 0.007531022678647839,
      "grad_norm": 0.1651465892791748,
      "learning_rate": 9.567727288213005e-05,
      "loss": 2.083,
      "step": 44
    },
    {
      "epoch": 0.007702182284980745,
      "grad_norm": 0.17137831449508667,
      "learning_rate": 9.53153893518325e-05,
      "loss": 2.0343,
      "step": 45
    },
    {
      "epoch": 0.00787334189131365,
      "grad_norm": 0.18124830722808838,
      "learning_rate": 9.493970231495835e-05,
      "loss": 1.8729,
      "step": 46
    },
    {
      "epoch": 0.008044501497646555,
      "grad_norm": 0.22116567194461823,
      "learning_rate": 9.45503262094184e-05,
      "loss": 1.8739,
      "step": 47
    },
    {
      "epoch": 0.008215661103979461,
      "grad_norm": 0.28191742300987244,
      "learning_rate": 9.414737964294636e-05,
      "loss": 2.0994,
      "step": 48
    },
    {
      "epoch": 0.008386820710312366,
      "grad_norm": 0.6001160144805908,
      "learning_rate": 9.373098535696979e-05,
      "loss": 2.1811,
      "step": 49
    },
    {
      "epoch": 0.008557980316645272,
      "grad_norm": 0.741450309753418,
      "learning_rate": 9.330127018922194e-05,
      "loss": 2.1858,
      "step": 50
    },
    {
      "epoch": 0.008557980316645272,
      "eval_loss": 2.0050954818725586,
      "eval_runtime": 259.0142,
      "eval_samples_per_second": 37.99,
      "eval_steps_per_second": 18.995,
      "step": 50
    },
    {
      "epoch": 0.008729139922978177,
      "grad_norm": 0.22430455684661865,
      "learning_rate": 9.285836503510562e-05,
      "loss": 1.8785,
      "step": 51
    },
    {
      "epoch": 0.008900299529311083,
      "grad_norm": 0.20247997343540192,
      "learning_rate": 9.24024048078213e-05,
      "loss": 1.9007,
      "step": 52
    },
    {
      "epoch": 0.009071459135643988,
      "grad_norm": 0.18127155303955078,
      "learning_rate": 9.193352839727121e-05,
      "loss": 1.9556,
      "step": 53
    },
    {
      "epoch": 0.009242618741976894,
      "grad_norm": 0.1620718389749527,
      "learning_rate": 9.145187862775209e-05,
      "loss": 1.8055,
      "step": 54
    },
    {
      "epoch": 0.009413778348309799,
      "grad_norm": 0.16836689412593842,
      "learning_rate": 9.09576022144496e-05,
      "loss": 1.7112,
      "step": 55
    },
    {
      "epoch": 0.009584937954642705,
      "grad_norm": 0.15607057511806488,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.7295,
      "step": 56
    },
    {
      "epoch": 0.00975609756097561,
      "grad_norm": 0.15433867275714874,
      "learning_rate": 8.993177550236464e-05,
      "loss": 1.7898,
      "step": 57
    },
    {
      "epoch": 0.009927257167308514,
      "grad_norm": 0.1581793874502182,
      "learning_rate": 8.940053768033609e-05,
      "loss": 1.8115,
      "step": 58
    },
    {
      "epoch": 0.01009841677364142,
      "grad_norm": 0.1593821793794632,
      "learning_rate": 8.885729807284856e-05,
      "loss": 1.8821,
      "step": 59
    },
    {
      "epoch": 0.010269576379974325,
      "grad_norm": 0.13692297041416168,
      "learning_rate": 8.83022221559489e-05,
      "loss": 1.9019,
      "step": 60
    },
    {
      "epoch": 0.010440735986307232,
      "grad_norm": 0.13366976380348206,
      "learning_rate": 8.773547901113862e-05,
      "loss": 1.8569,
      "step": 61
    },
    {
      "epoch": 0.010611895592640136,
      "grad_norm": 0.13981181383132935,
      "learning_rate": 8.715724127386972e-05,
      "loss": 2.0179,
      "step": 62
    },
    {
      "epoch": 0.010783055198973043,
      "grad_norm": 0.11422371119260788,
      "learning_rate": 8.656768508095853e-05,
      "loss": 1.9594,
      "step": 63
    },
    {
      "epoch": 0.010954214805305947,
      "grad_norm": 0.12120245397090912,
      "learning_rate": 8.596699001693255e-05,
      "loss": 1.9958,
      "step": 64
    },
    {
      "epoch": 0.011125374411638854,
      "grad_norm": 0.10169228911399841,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.9392,
      "step": 65
    },
    {
      "epoch": 0.011296534017971758,
      "grad_norm": 0.09632351249456406,
      "learning_rate": 8.473291852294987e-05,
      "loss": 1.8104,
      "step": 66
    },
    {
      "epoch": 0.011467693624304665,
      "grad_norm": 0.10891255736351013,
      "learning_rate": 8.409991800312493e-05,
      "loss": 2.1084,
      "step": 67
    },
    {
      "epoch": 0.01163885323063757,
      "grad_norm": 0.09422247111797333,
      "learning_rate": 8.345653031794292e-05,
      "loss": 1.8242,
      "step": 68
    },
    {
      "epoch": 0.011810012836970476,
      "grad_norm": 0.097730353474617,
      "learning_rate": 8.280295144952536e-05,
      "loss": 1.8866,
      "step": 69
    },
    {
      "epoch": 0.01198117244330338,
      "grad_norm": 0.0988590195775032,
      "learning_rate": 8.213938048432697e-05,
      "loss": 2.0188,
      "step": 70
    },
    {
      "epoch": 0.012152332049636286,
      "grad_norm": 0.09687261283397675,
      "learning_rate": 8.146601955249188e-05,
      "loss": 1.9782,
      "step": 71
    },
    {
      "epoch": 0.012323491655969191,
      "grad_norm": 0.10483600199222565,
      "learning_rate": 8.07830737662829e-05,
      "loss": 1.9285,
      "step": 72
    },
    {
      "epoch": 0.012494651262302097,
      "grad_norm": 0.10860675573348999,
      "learning_rate": 8.009075115760243e-05,
      "loss": 1.9643,
      "step": 73
    },
    {
      "epoch": 0.012665810868635002,
      "grad_norm": 0.10306871682405472,
      "learning_rate": 7.938926261462366e-05,
      "loss": 1.8897,
      "step": 74
    },
    {
      "epoch": 0.012836970474967908,
      "grad_norm": 0.09955226629972458,
      "learning_rate": 7.86788218175523e-05,
      "loss": 1.9064,
      "step": 75
    },
    {
      "epoch": 0.013008130081300813,
      "grad_norm": 0.11086455732584,
      "learning_rate": 7.795964517353735e-05,
      "loss": 1.9856,
      "step": 76
    },
    {
      "epoch": 0.013179289687633718,
      "grad_norm": 0.106622114777565,
      "learning_rate": 7.723195175075136e-05,
      "loss": 1.9768,
      "step": 77
    },
    {
      "epoch": 0.013350449293966624,
      "grad_norm": 0.11136943846940994,
      "learning_rate": 7.649596321166024e-05,
      "loss": 2.0076,
      "step": 78
    },
    {
      "epoch": 0.013521608900299529,
      "grad_norm": 0.10378699749708176,
      "learning_rate": 7.575190374550272e-05,
      "loss": 2.0183,
      "step": 79
    },
    {
      "epoch": 0.013692768506632435,
      "grad_norm": 0.10002272576093674,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.9106,
      "step": 80
    },
    {
      "epoch": 0.01386392811296534,
      "grad_norm": 0.10468745976686478,
      "learning_rate": 7.424048101231686e-05,
      "loss": 2.1109,
      "step": 81
    },
    {
      "epoch": 0.014035087719298246,
      "grad_norm": 0.1047583818435669,
      "learning_rate": 7.347357813929454e-05,
      "loss": 1.8169,
      "step": 82
    },
    {
      "epoch": 0.01420624732563115,
      "grad_norm": 0.11088533699512482,
      "learning_rate": 7.269952498697734e-05,
      "loss": 2.0148,
      "step": 83
    },
    {
      "epoch": 0.014377406931964057,
      "grad_norm": 0.11189869791269302,
      "learning_rate": 7.191855733945387e-05,
      "loss": 1.9053,
      "step": 84
    },
    {
      "epoch": 0.014548566538296961,
      "grad_norm": 0.11222604662179947,
      "learning_rate": 7.113091308703498e-05,
      "loss": 1.85,
      "step": 85
    },
    {
      "epoch": 0.014719726144629868,
      "grad_norm": 0.11671954393386841,
      "learning_rate": 7.033683215379002e-05,
      "loss": 1.8606,
      "step": 86
    },
    {
      "epoch": 0.014890885750962772,
      "grad_norm": 0.11258739233016968,
      "learning_rate": 6.953655642446368e-05,
      "loss": 1.9892,
      "step": 87
    },
    {
      "epoch": 0.015062045357295679,
      "grad_norm": 0.12018974870443344,
      "learning_rate": 6.873032967079561e-05,
      "loss": 2.0688,
      "step": 88
    },
    {
      "epoch": 0.015233204963628583,
      "grad_norm": 0.1348743736743927,
      "learning_rate": 6.7918397477265e-05,
      "loss": 1.9919,
      "step": 89
    },
    {
      "epoch": 0.01540436456996149,
      "grad_norm": 0.13200099766254425,
      "learning_rate": 6.710100716628344e-05,
      "loss": 1.9153,
      "step": 90
    },
    {
      "epoch": 0.015575524176294394,
      "grad_norm": 0.1338081955909729,
      "learning_rate": 6.627840772285784e-05,
      "loss": 1.7685,
      "step": 91
    },
    {
      "epoch": 0.0157466837826273,
      "grad_norm": 0.13655497133731842,
      "learning_rate": 6.545084971874738e-05,
      "loss": 1.9897,
      "step": 92
    },
    {
      "epoch": 0.015917843388960205,
      "grad_norm": 0.1462564319372177,
      "learning_rate": 6.461858523613684e-05,
      "loss": 1.692,
      "step": 93
    },
    {
      "epoch": 0.01608900299529311,
      "grad_norm": 0.16037926077842712,
      "learning_rate": 6.378186779084995e-05,
      "loss": 1.9882,
      "step": 94
    },
    {
      "epoch": 0.016260162601626018,
      "grad_norm": 0.16777467727661133,
      "learning_rate": 6.294095225512603e-05,
      "loss": 1.8377,
      "step": 95
    },
    {
      "epoch": 0.016431322207958923,
      "grad_norm": 0.21440783143043518,
      "learning_rate": 6.209609477998338e-05,
      "loss": 1.9863,
      "step": 96
    },
    {
      "epoch": 0.016602481814291827,
      "grad_norm": 0.23396961390972137,
      "learning_rate": 6.124755271719325e-05,
      "loss": 2.1281,
      "step": 97
    },
    {
      "epoch": 0.016773641420624732,
      "grad_norm": 0.29652488231658936,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 2.373,
      "step": 98
    },
    {
      "epoch": 0.016944801026957636,
      "grad_norm": 0.403049498796463,
      "learning_rate": 5.9540449768827246e-05,
      "loss": 2.1079,
      "step": 99
    },
    {
      "epoch": 0.017115960633290545,
      "grad_norm": 0.7542735934257507,
      "learning_rate": 5.868240888334653e-05,
      "loss": 2.4682,
      "step": 100
    },
    {
      "epoch": 0.017115960633290545,
      "eval_loss": 1.9593321084976196,
      "eval_runtime": 259.8209,
      "eval_samples_per_second": 37.872,
      "eval_steps_per_second": 18.936,
      "step": 100
    },
    {
      "epoch": 0.01728712023962345,
      "grad_norm": 0.11763519048690796,
      "learning_rate": 5.782172325201155e-05,
      "loss": 1.8203,
      "step": 101
    },
    {
      "epoch": 0.017458279845956354,
      "grad_norm": 0.1114693209528923,
      "learning_rate": 5.695865504800327e-05,
      "loss": 1.8145,
      "step": 102
    },
    {
      "epoch": 0.01762943945228926,
      "grad_norm": 0.1230073869228363,
      "learning_rate": 5.6093467170257374e-05,
      "loss": 1.8229,
      "step": 103
    },
    {
      "epoch": 0.017800599058622166,
      "grad_norm": 0.11512916535139084,
      "learning_rate": 5.522642316338268e-05,
      "loss": 1.7874,
      "step": 104
    },
    {
      "epoch": 0.01797175866495507,
      "grad_norm": 0.10919209569692612,
      "learning_rate": 5.435778713738292e-05,
      "loss": 1.7337,
      "step": 105
    },
    {
      "epoch": 0.018142918271287976,
      "grad_norm": 0.1077539324760437,
      "learning_rate": 5.348782368720626e-05,
      "loss": 1.8302,
      "step": 106
    },
    {
      "epoch": 0.01831407787762088,
      "grad_norm": 0.11689794063568115,
      "learning_rate": 5.26167978121472e-05,
      "loss": 1.9384,
      "step": 107
    },
    {
      "epoch": 0.01848523748395379,
      "grad_norm": 0.11336947977542877,
      "learning_rate": 5.174497483512506e-05,
      "loss": 1.7964,
      "step": 108
    },
    {
      "epoch": 0.018656397090286693,
      "grad_norm": 0.12187959998846054,
      "learning_rate": 5.0872620321864185e-05,
      "loss": 1.9133,
      "step": 109
    },
    {
      "epoch": 0.018827556696619598,
      "grad_norm": 0.11696886271238327,
      "learning_rate": 5e-05,
      "loss": 1.8401,
      "step": 110
    },
    {
      "epoch": 0.018998716302952502,
      "grad_norm": 0.12245535105466843,
      "learning_rate": 4.912737967813583e-05,
      "loss": 1.9705,
      "step": 111
    },
    {
      "epoch": 0.01916987590928541,
      "grad_norm": 0.128287672996521,
      "learning_rate": 4.825502516487497e-05,
      "loss": 1.9326,
      "step": 112
    },
    {
      "epoch": 0.019341035515618315,
      "grad_norm": 0.1252676546573639,
      "learning_rate": 4.738320218785281e-05,
      "loss": 1.9558,
      "step": 113
    },
    {
      "epoch": 0.01951219512195122,
      "grad_norm": 0.11466590315103531,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 1.8353,
      "step": 114
    },
    {
      "epoch": 0.019683354728284124,
      "grad_norm": 0.10190092772245407,
      "learning_rate": 4.564221286261709e-05,
      "loss": 1.796,
      "step": 115
    },
    {
      "epoch": 0.01985451433461703,
      "grad_norm": 0.12567828595638275,
      "learning_rate": 4.477357683661734e-05,
      "loss": 1.9864,
      "step": 116
    },
    {
      "epoch": 0.020025673940949937,
      "grad_norm": 0.11949620395898819,
      "learning_rate": 4.390653282974264e-05,
      "loss": 2.049,
      "step": 117
    },
    {
      "epoch": 0.02019683354728284,
      "grad_norm": 0.09391652792692184,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 1.7955,
      "step": 118
    },
    {
      "epoch": 0.020367993153615746,
      "grad_norm": 0.10908495634794235,
      "learning_rate": 4.2178276747988446e-05,
      "loss": 1.9891,
      "step": 119
    },
    {
      "epoch": 0.02053915275994865,
      "grad_norm": 0.10338300466537476,
      "learning_rate": 4.131759111665349e-05,
      "loss": 1.9437,
      "step": 120
    },
    {
      "epoch": 0.02071031236628156,
      "grad_norm": 0.09718688577413559,
      "learning_rate": 4.045955023117276e-05,
      "loss": 1.8637,
      "step": 121
    },
    {
      "epoch": 0.020881471972614463,
      "grad_norm": 0.10134649276733398,
      "learning_rate": 3.960441545911204e-05,
      "loss": 1.996,
      "step": 122
    },
    {
      "epoch": 0.021052631578947368,
      "grad_norm": 0.09256803244352341,
      "learning_rate": 3.875244728280676e-05,
      "loss": 1.8434,
      "step": 123
    },
    {
      "epoch": 0.021223791185280273,
      "grad_norm": 0.1016881987452507,
      "learning_rate": 3.790390522001662e-05,
      "loss": 1.9534,
      "step": 124
    },
    {
      "epoch": 0.02139495079161318,
      "grad_norm": 0.09520836174488068,
      "learning_rate": 3.705904774487396e-05,
      "loss": 1.8564,
      "step": 125
    },
    {
      "epoch": 0.021566110397946085,
      "grad_norm": 0.10661575943231583,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 2.0337,
      "step": 126
    },
    {
      "epoch": 0.02173727000427899,
      "grad_norm": 0.10315674543380737,
      "learning_rate": 3.5381414763863166e-05,
      "loss": 2.0366,
      "step": 127
    },
    {
      "epoch": 0.021908429610611894,
      "grad_norm": 0.10116354376077652,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 1.9307,
      "step": 128
    },
    {
      "epoch": 0.022079589216944803,
      "grad_norm": 0.09762448072433472,
      "learning_rate": 3.372159227714218e-05,
      "loss": 1.9752,
      "step": 129
    },
    {
      "epoch": 0.022250748823277707,
      "grad_norm": 0.09820623695850372,
      "learning_rate": 3.289899283371657e-05,
      "loss": 1.9644,
      "step": 130
    },
    {
      "epoch": 0.022421908429610612,
      "grad_norm": 0.10763833671808243,
      "learning_rate": 3.2081602522734986e-05,
      "loss": 2.062,
      "step": 131
    },
    {
      "epoch": 0.022593068035943516,
      "grad_norm": 0.10071827471256256,
      "learning_rate": 3.12696703292044e-05,
      "loss": 1.9037,
      "step": 132
    },
    {
      "epoch": 0.022764227642276424,
      "grad_norm": 0.10233649611473083,
      "learning_rate": 3.046344357553632e-05,
      "loss": 2.01,
      "step": 133
    },
    {
      "epoch": 0.02293538724860933,
      "grad_norm": 0.10517492145299911,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 1.9178,
      "step": 134
    },
    {
      "epoch": 0.023106546854942234,
      "grad_norm": 0.1058327928185463,
      "learning_rate": 2.886908691296504e-05,
      "loss": 1.8554,
      "step": 135
    },
    {
      "epoch": 0.02327770646127514,
      "grad_norm": 0.11381185799837112,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 1.9393,
      "step": 136
    },
    {
      "epoch": 0.023448866067608043,
      "grad_norm": 0.12022625654935837,
      "learning_rate": 2.7300475013022663e-05,
      "loss": 1.9708,
      "step": 137
    },
    {
      "epoch": 0.02362002567394095,
      "grad_norm": 0.12125593423843384,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 1.8177,
      "step": 138
    },
    {
      "epoch": 0.023791185280273856,
      "grad_norm": 0.12773887813091278,
      "learning_rate": 2.575951898768315e-05,
      "loss": 2.058,
      "step": 139
    },
    {
      "epoch": 0.02396234488660676,
      "grad_norm": 0.12078281491994858,
      "learning_rate": 2.500000000000001e-05,
      "loss": 2.0104,
      "step": 140
    },
    {
      "epoch": 0.024133504492939665,
      "grad_norm": 0.13929595053195953,
      "learning_rate": 2.4248096254497288e-05,
      "loss": 1.8098,
      "step": 141
    },
    {
      "epoch": 0.024304664099272573,
      "grad_norm": 0.1575964242219925,
      "learning_rate": 2.350403678833976e-05,
      "loss": 1.7819,
      "step": 142
    },
    {
      "epoch": 0.024475823705605478,
      "grad_norm": 0.16842733323574066,
      "learning_rate": 2.2768048249248648e-05,
      "loss": 1.9769,
      "step": 143
    },
    {
      "epoch": 0.024646983311938382,
      "grad_norm": 0.16018804907798767,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 1.8699,
      "step": 144
    },
    {
      "epoch": 0.024818142918271287,
      "grad_norm": 0.1840139478445053,
      "learning_rate": 2.132117818244771e-05,
      "loss": 1.8096,
      "step": 145
    },
    {
      "epoch": 0.024989302524604195,
      "grad_norm": 0.1963106095790863,
      "learning_rate": 2.061073738537635e-05,
      "loss": 1.9096,
      "step": 146
    },
    {
      "epoch": 0.0251604621309371,
      "grad_norm": 0.26290199160575867,
      "learning_rate": 1.9909248842397584e-05,
      "loss": 2.0225,
      "step": 147
    },
    {
      "epoch": 0.025331621737270004,
      "grad_norm": 0.36925578117370605,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 2.1319,
      "step": 148
    },
    {
      "epoch": 0.02550278134360291,
      "grad_norm": 0.43525442481040955,
      "learning_rate": 1.8533980447508137e-05,
      "loss": 2.0081,
      "step": 149
    },
    {
      "epoch": 0.025673940949935817,
      "grad_norm": 0.6942906379699707,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 2.3969,
      "step": 150
    },
    {
      "epoch": 0.025673940949935817,
      "eval_loss": 1.9431641101837158,
      "eval_runtime": 259.5615,
      "eval_samples_per_second": 37.91,
      "eval_steps_per_second": 18.955,
      "step": 150
    },
    {
      "epoch": 0.02584510055626872,
      "grad_norm": 0.10920389741659164,
      "learning_rate": 1.7197048550474643e-05,
      "loss": 2.0639,
      "step": 151
    },
    {
      "epoch": 0.026016260162601626,
      "grad_norm": 0.1058569997549057,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 2.0846,
      "step": 152
    },
    {
      "epoch": 0.02618741976893453,
      "grad_norm": 0.09319698065519333,
      "learning_rate": 1.5900081996875083e-05,
      "loss": 1.9202,
      "step": 153
    },
    {
      "epoch": 0.026358579375267435,
      "grad_norm": 0.08622536808252335,
      "learning_rate": 1.526708147705013e-05,
      "loss": 1.8637,
      "step": 154
    },
    {
      "epoch": 0.026529738981600343,
      "grad_norm": 0.0853772908449173,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 1.7182,
      "step": 155
    },
    {
      "epoch": 0.026700898587933248,
      "grad_norm": 0.08946704864501953,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 1.6587,
      "step": 156
    },
    {
      "epoch": 0.026872058194266153,
      "grad_norm": 0.09572125226259232,
      "learning_rate": 1.3432314919041478e-05,
      "loss": 1.8989,
      "step": 157
    },
    {
      "epoch": 0.027043217800599057,
      "grad_norm": 0.08904409408569336,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 1.8118,
      "step": 158
    },
    {
      "epoch": 0.027214377406931965,
      "grad_norm": 0.08511435985565186,
      "learning_rate": 1.22645209888614e-05,
      "loss": 1.8082,
      "step": 159
    },
    {
      "epoch": 0.02738553701326487,
      "grad_norm": 0.0909525528550148,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 1.8589,
      "step": 160
    },
    {
      "epoch": 0.027556696619597774,
      "grad_norm": 0.08706987649202347,
      "learning_rate": 1.1142701927151456e-05,
      "loss": 1.8641,
      "step": 161
    },
    {
      "epoch": 0.02772785622593068,
      "grad_norm": 0.08948656171560287,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 1.9488,
      "step": 162
    },
    {
      "epoch": 0.027899015832263587,
      "grad_norm": 0.08457276225090027,
      "learning_rate": 1.006822449763537e-05,
      "loss": 1.7138,
      "step": 163
    },
    {
      "epoch": 0.028070175438596492,
      "grad_norm": 0.08955824375152588,
      "learning_rate": 9.549150281252633e-06,
      "loss": 1.8604,
      "step": 164
    },
    {
      "epoch": 0.028241335044929396,
      "grad_norm": 0.09826652705669403,
      "learning_rate": 9.042397785550405e-06,
      "loss": 2.0011,
      "step": 165
    },
    {
      "epoch": 0.0284124946512623,
      "grad_norm": 0.0958012118935585,
      "learning_rate": 8.548121372247918e-06,
      "loss": 1.8258,
      "step": 166
    },
    {
      "epoch": 0.02858365425759521,
      "grad_norm": 0.09440874308347702,
      "learning_rate": 8.066471602728803e-06,
      "loss": 1.8542,
      "step": 167
    },
    {
      "epoch": 0.028754813863928114,
      "grad_norm": 0.09099198877811432,
      "learning_rate": 7.597595192178702e-06,
      "loss": 1.8798,
      "step": 168
    },
    {
      "epoch": 0.02892597347026102,
      "grad_norm": 0.08986622840166092,
      "learning_rate": 7.1416349648943894e-06,
      "loss": 1.8701,
      "step": 169
    },
    {
      "epoch": 0.029097133076593923,
      "grad_norm": 0.09858426451683044,
      "learning_rate": 6.698729810778065e-06,
      "loss": 1.9576,
      "step": 170
    },
    {
      "epoch": 0.02926829268292683,
      "grad_norm": 0.09769254922866821,
      "learning_rate": 6.269014643030213e-06,
      "loss": 1.9811,
      "step": 171
    },
    {
      "epoch": 0.029439452289259736,
      "grad_norm": 0.09606175124645233,
      "learning_rate": 5.852620357053651e-06,
      "loss": 1.9064,
      "step": 172
    },
    {
      "epoch": 0.02961061189559264,
      "grad_norm": 0.09492043405771255,
      "learning_rate": 5.449673790581611e-06,
      "loss": 1.8703,
      "step": 173
    },
    {
      "epoch": 0.029781771501925545,
      "grad_norm": 0.10341862589120865,
      "learning_rate": 5.060297685041659e-06,
      "loss": 2.0631,
      "step": 174
    },
    {
      "epoch": 0.02995293110825845,
      "grad_norm": 0.09646780043840408,
      "learning_rate": 4.684610648167503e-06,
      "loss": 1.841,
      "step": 175
    },
    {
      "epoch": 0.030124090714591358,
      "grad_norm": 0.10269562900066376,
      "learning_rate": 4.322727117869951e-06,
      "loss": 1.9051,
      "step": 176
    },
    {
      "epoch": 0.030295250320924262,
      "grad_norm": 0.09988216310739517,
      "learning_rate": 3.974757327377981e-06,
      "loss": 1.7797,
      "step": 177
    },
    {
      "epoch": 0.030466409927257167,
      "grad_norm": 0.10074089467525482,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 1.9299,
      "step": 178
    },
    {
      "epoch": 0.03063756953359007,
      "grad_norm": 0.10246999561786652,
      "learning_rate": 3.3209786751399187e-06,
      "loss": 1.7814,
      "step": 179
    },
    {
      "epoch": 0.03080872913992298,
      "grad_norm": 0.10588832944631577,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 1.9546,
      "step": 180
    },
    {
      "epoch": 0.030979888746255884,
      "grad_norm": 0.1015346571803093,
      "learning_rate": 2.724071220034158e-06,
      "loss": 1.7922,
      "step": 181
    },
    {
      "epoch": 0.03115104835258879,
      "grad_norm": 0.10796988755464554,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 1.9276,
      "step": 182
    },
    {
      "epoch": 0.0313222079589217,
      "grad_norm": 0.11297585815191269,
      "learning_rate": 2.1847622018482283e-06,
      "loss": 1.8389,
      "step": 183
    },
    {
      "epoch": 0.0314933675652546,
      "grad_norm": 0.1056937500834465,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 1.9095,
      "step": 184
    },
    {
      "epoch": 0.031664527171587506,
      "grad_norm": 0.12039455026388168,
      "learning_rate": 1.70370868554659e-06,
      "loss": 2.0558,
      "step": 185
    },
    {
      "epoch": 0.03183568677792041,
      "grad_norm": 0.11395536363124847,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 1.9243,
      "step": 186
    },
    {
      "epoch": 0.032006846384253315,
      "grad_norm": 0.12952271103858948,
      "learning_rate": 1.2814967607382432e-06,
      "loss": 1.9861,
      "step": 187
    },
    {
      "epoch": 0.03217800599058622,
      "grad_norm": 0.1313721239566803,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 1.9188,
      "step": 188
    },
    {
      "epoch": 0.032349165596919124,
      "grad_norm": 0.12433289736509323,
      "learning_rate": 9.186408276168013e-07,
      "loss": 1.8628,
      "step": 189
    },
    {
      "epoch": 0.032520325203252036,
      "grad_norm": 0.13518026471138,
      "learning_rate": 7.596123493895991e-07,
      "loss": 1.8971,
      "step": 190
    },
    {
      "epoch": 0.03269148480958494,
      "grad_norm": 0.1454542577266693,
      "learning_rate": 6.15582970243117e-07,
      "loss": 1.9262,
      "step": 191
    },
    {
      "epoch": 0.032862644415917845,
      "grad_norm": 0.14247220754623413,
      "learning_rate": 4.865965629214819e-07,
      "loss": 1.9895,
      "step": 192
    },
    {
      "epoch": 0.03303380402225075,
      "grad_norm": 0.15429534018039703,
      "learning_rate": 3.7269241793390085e-07,
      "loss": 2.0931,
      "step": 193
    },
    {
      "epoch": 0.033204963628583654,
      "grad_norm": 0.1652837097644806,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 1.9644,
      "step": 194
    },
    {
      "epoch": 0.03337612323491656,
      "grad_norm": 0.19331246614456177,
      "learning_rate": 1.9026509541272275e-07,
      "loss": 1.6578,
      "step": 195
    },
    {
      "epoch": 0.033547282841249464,
      "grad_norm": 0.20510539412498474,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 1.7814,
      "step": 196
    },
    {
      "epoch": 0.03371844244758237,
      "grad_norm": 0.23357729613780975,
      "learning_rate": 6.852326227130834e-08,
      "loss": 1.9337,
      "step": 197
    },
    {
      "epoch": 0.03388960205391527,
      "grad_norm": 0.2640667259693146,
      "learning_rate": 3.04586490452119e-08,
      "loss": 1.9994,
      "step": 198
    },
    {
      "epoch": 0.034060761660248184,
      "grad_norm": 0.4026579260826111,
      "learning_rate": 7.615242180436522e-09,
      "loss": 2.2905,
      "step": 199
    },
    {
      "epoch": 0.03423192126658109,
      "grad_norm": 0.6005451679229736,
      "learning_rate": 0.0,
      "loss": 2.5523,
      "step": 200
    },
    {
      "epoch": 0.03423192126658109,
      "eval_loss": 1.943039059638977,
      "eval_runtime": 260.198,
      "eval_samples_per_second": 37.817,
      "eval_steps_per_second": 18.909,
      "step": 200
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 7688467500761088.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}